execution/security-executor
Skill2 starsChanged 8 months agoMITView on GitHub
Internal: Security Executor. Implements auth, authorization, validation, crypto, secret-handling, and vulnerability remediations. Write evidence on completion.
In this repository34 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- auditSkill
- calibrationSkill
- dashboardSkill
- dry-runSkill
- executeSkill
- execution/backend-executorSkill
- execution/data-executorSkill
- execution/db-executorSkill
- execution/infra-executorSkill
- execution/integration-executorSkill
- execution/ml-executorSkill
- execution/observability-executorSkill
- execution/refactor-executorSkill
- execution/release-executorSkill
- executionSkill
- execution/testing-executorSkill
- execution/ui-executorSkill
- globalSkill
- initSkill
- investigateSkill
- listSkill
- localSkill
- maintainSkill
- memorySkill
- planSkill
- registerSkill
- repairSkill
- residualSkill
- resumeSkill
- startSkill
- statusSkill
- trajectorySkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Do not patch symptoms while leaving the attack path alive.
- Distinctive: line 13
Every security fix must name the trusted boundary and enforce it in code.
- Distinctive: line 14
If a mitigation is only convention, it is not a mitigation.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
dynos-work: execution/security-executor
Spawn the security-executor agent with the user's prompt as the instruction.
Ruthlessness Standard
- Do not patch symptoms while leaving the attack path alive.
- Every security fix must name the trusted boundary and enforce it in code.
- If a mitigation is only convention, it is not a mitigation.
What to pass
Pass the user's full prompt verbatim. Do not summarize or sanitize it. Prepend a short hard wrapper that tells the agent to close the exploit mechanism, verify negative paths, and write evidence only after the vulnerable route is no longer viable.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.